© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103754
    Prev
    Next
    INDEX
    Explanations

    expressions of moral objections and societal concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .mock
    -0.07
     mock
    -0.07
     Meaning
    -0.06
     tap
    -0.06
     moderation
    -0.06
    568
    -0.05
    bon
    -0.05
    ual
    -0.05
     mc
    -0.05
     Peace
    -0.05
    POSITIVE LOGITS
    Should
    0.08
     norge
    0.08
     permanently
    0.07
    Intialized
    0.07
    nnen
    0.07
    Permanent
    0.07
     cond
    0.07
    permanent
    0.07
    rique
    0.07
    ÏģÎŃ
    0.07
    Activations Density 0.058%

    No Known Activations